Acer · GB10 Grace Blackwell · 128 GB · Qwen3.8 27B · Q4_K_M: ~11 tok/s
Acer Veriton GN100
Acer's GB10 box: the same chip, 128 GB and 273 GB/s as the DGX Spark, with 2 TB of storage. Everything that runs on a Spark runs here.
Lowest price right now
$6,367.19
eBay · $6,349.99 + $17.20 shipping · $49 per GB · observed 2026-10-14 22:19 UTC
Where to buy
| Vendor | Price | Condition | Observed | |
|---|---|---|---|---|
| eBay cheapest active listing |
$6,367.19 $6,349.99 + $17.20 shipping |
new and used | 2026-10-14 22:19 UTC | Go to eBay |
On eBay now
2 listings passed our filters at the last check. Cheapest delivered first. Seller reputation is feedback count and positive rate.
-
$6,367.19$6,349.99 + $17.20 shipping -
$12,720$12,699 + $21 shipping
What it runs
For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.
| Model | Quant | Needs at 8K | Fit | Max context | Decode tok/s | Prefill tok/s |
|---|---|---|---|---|---|---|
| DeepSeek | ||||||
| DeepSeek V4.1 Flash 552B-A16B Sep 2026 | Q4_K_M | 338 GB | does not fit | |||
| DeepSeek V4 Flash 284B-A13B Jul 2026 | IQ2_M | 98 GB | fits | 128K+ | ~40 | ~1,700 |
| DeepSeek V3.1 671B-A37B Aug 2025 | Q4_K_M | 411 GB | does not fit | |||
| Gemma | ||||||
| Gemma 4 12B May 2026 | Q8_0 | 14 GB | fits | 128K+ | ~14 | ~1,800 |
| Gemma 4 31B Mar 2026 | Q8_0 | 35 GB | fits | 128K+ | ~5.5 | ~710 |
| Gemma 4 26B-A4B Mar 2026 | Q8_0 | 28 GB | fits | 128K+ | ~44 | ~5,800 |
| Gemma 3 27B Mar 2025 | Q8_0 | 31 GB | fits | 128K+ | ~6.1 | ~800 |
| GLM | ||||||
| GLM-5.3 753B-A40B Aug 2026 | Q4_K_M | 462 GB | does not fit | |||
| GLM-5.3 Flash 320B-A18B Aug 2026 | IQ2_M | 111 GB | fits | 128K+ | ~29 | ~1,200 |
| GLM-4.6 355B-A32B Sep 2025 | IQ2_M | 125 GB | fits | 15K | ~16 | ~680 |
| GLM-4.5 Air 106B-A12B Jul 2025 | Q8_0 | 115 GB | fits | 73K | ~14 | ~1,800 |
| gpt-oss | ||||||
| gpt-oss-120b Aug 2025 | Q8_0 | 126 GB | fits | 35K | ~33 | ~4,300 |
| gpt-oss-20b Aug 2025 | Q8_0 | 24 GB | fits | 128K+ | ~47 | ~6,100 |
| Llama | ||||||
| Llama 4 Scout 109B-A17B Apr 2025 | Q8_0 | 119 GB | fits | 54K | ~9.8 | ~1,300 |
| Llama 3.3 70B Dec 2024 | Q8_0 | 79 GB | fits | 128K+ | ~2.4 | ~310 |
| Llama 3.1 8B Jul 2024 | Q8_0 | 11 GB | fits | 128K+ | ~21 | ~2,700 |
| MiMo | ||||||
| MiMo V2.6 Pro 1.02T-A42B Sep 2026 | Q4_K_M | 624 GB | does not fit | |||
| MiMo V2.6 Flash 309B-A15B Sep 2026 | IQ2_M | 107 GB | fits | 128K+ | ~35 | ~1,500 |
| Mistral | ||||||
| Mistral Medium 3.5 128B Mar 2026 | Q6_K | 109 GB | fits | 58K | ~1.7 | ~170 |
| Mistral Small 4 119B-A6.5B Mar 2026 | Q6_K | 104 GB | fits | 47K | ~33 | ~3,400 |
| Mistral Small 3.2 24B Jun 2025 | Q8_0 | 28 GB | fits | 128K+ | ~7.0 | ~910 |
| Qwen | ||||||
| Qwen3.8 Flash-Next 125B-A6B Aug 2026 | Q6_K | 104 GB | fits | 128K+ | ~36 | ~3,600 |
| Qwen3.8 27B Aug 2026 (your pick) | Q8_0 | 31 GB | fits | 128K+ | ~6.2 | ~810 |
| Qwen3.6 27B Apr 2026 | Q8_0 | 31 GB | fits | 128K+ | ~6.2 | ~810 |
| Qwen3.6 35B-A3B Apr 2026 | Q8_0 | 39 GB | fits | 128K+ | ~56 | ~7,300 |
| Qwen3 Coder 480B-A35B Jul 2025 | Q4_K_M | 296 GB | does not fit | |||
| Qwen3 235B-A22B Jul 2025 | Q3_K_M | 118 GB | fits | 57K | ~16 | ~990 |
| Qwen3 32B Apr 2025 | Q8_0 | 38 GB | fits | 128K+ | ~5.1 | ~670 |
Specifications
- Memory
- 128 GB LPDDR5x unified
- Memory bandwidth
- 273 GB/s
- Bus width
- 256-bit
- Shader cores
- 6,144
- Tensor cores
- 192
- FP16 (dense)
- 125 TFLOPS
- FP8 (dense)
- 250 TFLOPS
- Power
- 240 W
- Form factor
- Desktop box
- CPU
- 20-core Arm (10x Cortex-X925 + 10x Cortex-A725)
- Architecture
- GB10 Grace Blackwell
- Launched
- 2025
- MSRP
- $3,999
Source: manufacturer specifications.